Big Data and Emerging Transportation Challenges: Findings from the NOESIS project

In the last years many Big Data technologies have been applied to the transportation sector all over the world. Despite existing and future promising applications, critical factors which lead to a successful application and value generation from Big Data technologies in transport are largely unknown. The European Union (EU) Horizon 2020 (H2020) NOESIS project aims at identifying critical features leading to the successful implementation of Big Data technologies and services in the field of transport. In order to accomplish that aim, key challenges of Big Data utilization in the transport domain, need to be initially identified. The scope of this paper is to present the research findings on the major Big Data in Transportation challenges. The NOESIS challenges describe the major transportation areas and sub-problems that could benefit by Big Data. Firstly, a literature review was conducted in order to obtain the main areas (challenges) within the transportation domain which have the potential of greater exploitation through Big Data methods. 10 initial focus areas were identified from reviewing the state-of-the-art in Big Data and transportation research. Secondly, findings from the literature review were discussed and validated during a workshop with experts on Big Data in Transportation, increasing those challenges to 13. For each of the focus areas, corresponding sub-problems have been also identified. The findings of this paper contribute to the exploitation of Big Data within transportation in two ways: i) it provides the necessary literature review and experts' discussion for identifying the transport domain areas in which big data technologies could be successfully applied and ii) it identifies sub-problems linked to each of the challenges that big data could help to improve transportation. As a result, it is believed that this work initiates a first step towards enhancing the socioeconomic impact of transportation investments using Big Data.